|
--- |
|
license: apache-2.0 |
|
language: |
|
- en |
|
--- |
|
# NeuralMaxime-7B-slerp-GGUF |
|
|
|
|
|
## Description |
|
|
|
This repo contains GGUF format model files for NeuralMaxime-7B-slerp-GGUF. |
|
|
|
## Files Provided |
|
|
|
| Name | Quant | Bits | File Size | Remark | |
|
| --------------------------------- | ------ | ---- | --------- | -------------------------------- | |
|
| neuralmaxime-7b-slerp.IQ3_S.gguf | IQ3_S | 3 | 3.18 GB | 3.44 bpw quantization | |
|
| neuralmaxime-7b-slerp.IQ3_M.gguf | IQ3_M | 3 | 3.28 GB | 3.66 bpw quantization mix | |
|
| neuralmaxime-7b-slerp.Q4_0.gguf | Q4_0 | 4 | 4.11 GB | 3.56G, +0.2166 ppl | |
|
| neuralmaxime-7b-slerp.IQ4_NL.gguf | IQ4_NL | 4 | 4.16 GB | 4.25 bpw non-linear quantization | |
|
| neuralmaxime-7b-slerp.Q4_K_M.gguf | Q4_K_M | 4 | 4.37 GB | 3.80G, +0.0532 ppl | |
|
| neuralmaxime-7b-slerp.Q5_K_M.gguf | Q5_K_M | 5 | 5.13 GB | 4.45G, +0.0122 ppl | |
|
| neuralmaxime-7b-slerp.Q6_K.gguf | Q6_K | 6 | 5.94 GB | 5.15G, +0.0008 ppl | |
|
| neuralmaxime-7b-slerp.Q8_0.gguf | Q8_0 | 8 | 7.70 GB | 6.70G, +0.0004 ppl | |
|
|
|
## Parameters |
|
|
|
| path | type | architecture | rope_theta | sliding_win | max_pos_embed | |
|
| ----------------------------- | ------- | ------------------ | ---------- | ----------- | ------------- | |
|
| Kukedlc/NeuralMaxime-7B-slerp | mistral | MistralForCausalLM | 10000.0 | 4096 | 32768 | |
|
|
|
## Benchmarks |
|
|
|
![](https://i.ibb.co/g7sqr1r/Neural-Maxime-7-B-slerp.png) |
|
|
|
# Original Model Card |
|
|
|
--- |
|
tags: |
|
- merge |
|
- mergekit |
|
- lazymergekit |
|
- mlabonne/AlphaMonarch-7B |
|
- mlabonne/NeuralMonarch-7B |
|
base_model: |
|
- mlabonne/AlphaMonarch-7B |
|
- mlabonne/NeuralMonarch-7B |
|
license: apache-2.0 |
|
--- |
|
|
|
# NeuralMaxime-7B-slerp |
|
|
|
![](https://raw.githubusercontent.com/kukedlc87/imagenes/main/DALL%C2%B7E%202024-02-18%2015.45.07%20-%20Visualize%20a%20highly%20sophisticated%2C%20high-definition%20robot%20named%20Neural%20Maxime.%20This%20language%20model%20robot%20is%20distinguished%20by%20its%20innovative%20design%2C%20feat.webp) |
|
NeuralMaxime-7B-slerp is a merge of the following models using [LazyMergekit](https://colab.research.google.com/drive/1obulZ1ROXHjYLn6PPZJwRR6GzgQogxxb?usp=sharing): |
|
* [mlabonne/AlphaMonarch-7B](https://huggingface.co/mlabonne/AlphaMonarch-7B) |
|
* [mlabonne/NeuralMonarch-7B](https://huggingface.co/mlabonne/NeuralMonarch-7B) |
|
|
|
## 🧩 Configuration |
|
|
|
```yaml |
|
slices: |
|
- sources: |
|
- model: mlabonne/AlphaMonarch-7B |
|
layer_range: [0, 32] |
|
- model: mlabonne/NeuralMonarch-7B |
|
layer_range: [0, 32] |
|
merge_method: slerp |
|
base_model: mlabonne/AlphaMonarch-7B |
|
parameters: |
|
t: |
|
- filter: self_attn |
|
value: [0, 0.5, 0.3, 0.7, 1] |
|
- filter: mlp |
|
value: [1, 0.5, 0.7, 0.3, 0] |
|
- value: 0.5 |
|
dtype: bfloat16 |
|
``` |
|
|
|
## 💻 Usage |
|
|
|
```python |
|
!pip install -qU transformers accelerate |
|
|
|
from transformers import AutoTokenizer |
|
import transformers |
|
import torch |
|
|
|
model = "Kukedlc/NeuralMaxime-7B-slerp" |
|
messages = [{"role": "user", "content": "What is a large language model?"}] |
|
|
|
tokenizer = AutoTokenizer.from_pretrained(model) |
|
prompt = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True) |
|
pipeline = transformers.pipeline( |
|
"text-generation", |
|
model=model, |
|
torch_dtype=torch.float16, |
|
device_map="auto", |
|
) |
|
|
|
outputs = pipeline(prompt, max_new_tokens=256, do_sample=True, temperature=0.7, top_k=50, top_p=0.95) |
|
print(outputs[0]["generated_text"]) |
|
``` |